all InfoSec news
MedBN: Robust Test-Time Adaptation against Malicious Test Samples
March 29, 2024, 4:11 a.m. | Hyejin Park, Jeongyeon Hwang, Sunung Mun, Sangdon Park, Jungseul Ok
cs.CR updates on arXiv.org arxiv.org
Abstract: Test-time adaptation (TTA) has emerged as a promising solution to address performance decay due to unforeseen distribution shifts between training and test data. While recent TTA methods excel in adapting to test data variations, such adaptability exposes a model to vulnerability against malicious examples, an aspect that has received limited attention. Previous studies have uncovered security vulnerabilities within TTA even when a small proportion of the test batch is maliciously manipulated. In response to the …
adaptability adaptation address arxiv aspect cs.cr cs.cv cs.lg data distribution examples excel malicious performance shifts solution test training vulnerability
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
CyberSOC Technical Lead
@ Integrity360 | Sandyford, Dublin, Ireland
Cyber Security Strategy Consultant
@ Capco | New York City
Cyber Security Senior Consultant
@ Capco | Chicago, IL
Sr. Product Manager
@ MixMode | Remote, US
Corporate Intern - Information Security (Year Round)
@ Associated Bank | US WI Remote
Senior Offensive Security Engineer
@ CoStar Group | US-DC Washington, DC